Flagship Indian-language reasoning model for enterprise multilingual applicationsSarvam 105B is offered by 3 providers on this page. Its official list price is $0.158 per 1M input tokens and $0.632 per 1M output tokens. The lowest paid channel is FastRouter at $0.04 / $0.16 per 1M, about 3.9× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Median output speed is 413 tokens per second, with 1.52s to the first token.
The context window is 131,072 tokens, with an output limit of 131,072 tokens. It supports reasoning and tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| FastRouter | Gateway | $0.04 | $0.16 | $0.025 | — | 131,072 | 131,072 | |
| NanoGPT | Gateway | $0.054 | $0.21 | $0.034 | — | 131,072 | 4,096 | |
| Sarvam AIOfficial | First-party | $0.16 | $0.63 | $0.053 | — | 131,072 | 131,072 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 3 providers.
1 / 3 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.